Create README.md

README.md

@@ -0,0 +1,60 @@
+---
+library_name: diffusers
+base_model: runwayml/stable-diffusion-v1-5
+tags:
+- text-to-image
+license: creativeml-openrail-m
+inference: true
+---
+
+## yujiepan/dreamshaper-8-lcm-openvino
+
+This model applies [latent-consistency/lcm-lora-sdv1-5](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5)
+on base model [Lykon/dreamshaper-8](https://huggingface.co/Lykon/dreamshaper-8), and is converted as OpenVINO **FP16** format.
+
+#### Usage
+
+```python
+from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionPipeline
+pipeline = OVStableDiffusionPipeline.from_pretrained(
+    'yujiepan/dreamshaper-8-lcm-openvino',
+    device='CPU',
+)
+prompt = 'cute dog typing at a laptop, 4k, details'
+images = pipeline(prompt=prompt, num_inference_steps=8, guidance_scale=1.0).images
+```
+
+![output image](./assets/cute-dog-typing-at-a-laptop-4k-details.png)
+
+
+#### Scripts
+
+The model is generated by the following codes:
+
+```python
+import torch
+from diffusers import AutoPipelineForText2Image, LCMScheduler
+from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionPipeline
+
+base_model_id = "Lykon/dreamshaper-8"
+adapter_id = "latent-consistency/lcm-lora-sdv1-5"
+save_torch_folder = './dreamshaper-8-lcm'
+save_ov_folder = './dreamshaper-8-lcm-openvino'
+
+torch_pipeline = AutoPipelineForText2Image.from_pretrained(
+    base_model_id, torch_dtype=torch.float16, variant="fp16")
+torch_pipeline.scheduler = LCMScheduler.from_config(
+    torch_pipeline.scheduler.config)
+# load and fuse lcm lora
+torch_pipeline.load_lora_weights(adapter_id)
+torch_pipeline.fuse_lora()
+torch_pipeline.save_pretrained(save_torch_folder)
+
+ov_pipeline = OVStableDiffusionPipeline.from_pretrained(
+    save_torch_folder,
+    device='CPU',
+    export=True,
+)
+ov_pipeline.half()
+ov_pipeline.save_pretrained(save_ov_folder)
+```